SkillRepo
Sign InSign Up
Catalog
mattpocock/to-prd

mattpocock

to-prd

Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.

global
0installs0uses—~690
v1.0Saved May 2, 2026

This skill takes the current conversation context and codebase understanding and produces a PRD. Do NOT interview the user — just synthesize what you already know.

The issue tracker and triage label vocabulary should have been provided to you — run /setup-matt-pocock-skills if not.

Process

  1. Explore the repo to understand the current state of the codebase, if you haven't already. Use the project's domain glossary vocabulary throughout the PRD, and respect any ADRs in the area you're touching.

  2. Sketch out the major modules you will need to build or modify to complete the implementation. Actively look for opportunities to extract deep modules that can be tested in isolation.

A deep module (as opposed to a shallow module) is one which encapsulates a lot of functionality in a simple, testable interface which rarely changes.

Check with the user that these modules match their expectations. Check with the user which modules they want tests written for.

  1. Write the PRD using the template below, then publish it to the project issue tracker. Apply the needs-triage triage label so it enters the normal triage flow.

Problem Statement

The problem that the user is facing, from the user's perspective.

Solution

The solution to the problem, from the user's perspective.

User Stories

A LONG, numbered list of user stories. Each user story should be in the format of:

  1. As an , I want a , so that

This list of user stories should be extremely extensive and cover all aspects of the feature.

Implementation Decisions

A list of implementation decisions that were made. This can include:

  • The modules that will be built/modified
  • The interfaces of those modules that will be modified
  • Technical clarifications from the developer
  • Architectural decisions
  • Schema changes
  • API contracts
  • Specific interactions

Do NOT include specific file paths or code snippets. They may end up being outdated very quickly.

Testing Decisions

A list of testing decisions that were made. Include:

  • A description of what makes a good test (only test external behavior, not implementation details)
  • Which modules will be tested
  • Prior art for the tests (i.e. similar types of tests in the codebase)

Out of Scope

A description of the things that are out of scope for this PRD.

Further Notes

Any further notes about the feature.

Files1
1 files · 1.0 KB

Select a file to preview

Overall Score

71/100

Grade

B

Good

Safety

78

Quality

68

Clarity

75

Completeness

62

Summary

This skill synthesizes current conversation context and codebase understanding into a structured Product Requirements Document (PRD), then publishes it to a project issue tracker. It guides an agent through codebase exploration, module architecture design, and PRD generation using a provided template, with user validation checkpoints for module design and testing scope.

Detected Capabilities

Codebase exploration and state assessmentDomain glossary and ADR integrationModule architecture design and deep module identificationPRD generation from template with structured sectionsIssue tracker integration and triage label applicationUser validation checkpoints for design decisions

Trigger Keywords

Phrases that MCP clients use to match this skill to user intent.

create prd from conversationwrite product requirementsissue tracker publicationsynthesize feature specarchitecture design document

Risk Signals

WARNING

Dependency on external setup skill (/setup-matt-pocock-skills) for issue tracker credentials and triage vocabulary

SKILL.md: 'The issue tracker and triage label vocabulary should have been provided to you — run `/setup-matt-pocock-skills` if not.'
WARNING

No documented guardrails for issue tracker access permissions or validation

SKILL.md: Process step 3 publishes directly to issue tracker without documented authorization checks
INFO

Implicit assumption that conversation context is complete and accurate

SKILL.md: 'Do NOT interview the user — just synthesize what you already know.'
WARNING

No error handling documented for failed issue tracker publishes or malformed PRD generation

SKILL.md: entire Process section

Use Cases

  • Convert informal feature discussion into formal PRD for team alignment
  • Document architectural decisions and module design before implementation
  • Create issue tracker artifacts from conversation context to drive development workflow
  • Synthesize codebase understanding into specification documents for cross-functional teams

Quality Notes

  • Clear, well-structured PRD template with all necessary sections (Problem, Solution, User Stories, Implementation Decisions, Testing, Out of Scope, Further Notes)
  • Good guidance on deep modules — explains the architectural principle and why it matters
  • Process is logical with clear numbered steps and user validation checkpoints
  • Missing documentation on how the skill determines current conversation context — unclear if it's automatic or requires agent to specify
  • No guidance on handling edge cases: what if repo is in an inconsistent state? What if user stories conflict with implementation constraints?
  • Template guidance is strong (e.g., 'LONG, numbered list' of user stories, 'Do NOT include specific file paths') but skill lacks error handling for when template is incomplete
  • Dependencies on external skills (setup-matt-pocock-skills, domain glossary, ADRs) are assumed but not validated
  • No documented output format — unclear whether agent should return raw PRD text, markdown file, or structured JSON for issue tracker integration
Model: claude-haiku-4-5-20251001Analyzed: May 2, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Add mattpocock/to-prd to your library

Get Started Free

Command Palette

Search for a command to run...